| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.026975991367682764, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005395198273536552, | |
| "eval_loss": 2.106476306915283, | |
| "eval_runtime": 48.0889, | |
| "eval_samples_per_second": 16.241, | |
| "eval_steps_per_second": 8.131, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002697599136768276, | |
| "grad_norm": 6.246270179748535, | |
| "learning_rate": 5e-05, | |
| "loss": 8.6301, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.005395198273536552, | |
| "grad_norm": 6.861983299255371, | |
| "learning_rate": 0.0001, | |
| "loss": 8.3854, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.005395198273536552, | |
| "eval_loss": 2.05218768119812, | |
| "eval_runtime": 48.5803, | |
| "eval_samples_per_second": 16.076, | |
| "eval_steps_per_second": 8.049, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.008092797410304829, | |
| "grad_norm": 8.243408203125, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 8.0358, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.010790396547073105, | |
| "grad_norm": 8.477263450622559, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 8.5592, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.010790396547073105, | |
| "eval_loss": 2.0519731044769287, | |
| "eval_runtime": 48.3623, | |
| "eval_samples_per_second": 16.149, | |
| "eval_steps_per_second": 8.085, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.013487995683841382, | |
| "grad_norm": 7.101188659667969, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 8.3489, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.016185594820609658, | |
| "grad_norm": 7.083747863769531, | |
| "learning_rate": 5e-05, | |
| "loss": 8.2269, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.016185594820609658, | |
| "eval_loss": 2.0463201999664307, | |
| "eval_runtime": 48.4484, | |
| "eval_samples_per_second": 16.12, | |
| "eval_steps_per_second": 8.07, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.018883193957377933, | |
| "grad_norm": 8.091001510620117, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 7.7337, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.02158079309414621, | |
| "grad_norm": 7.108482837677002, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 8.3231, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.02158079309414621, | |
| "eval_loss": 2.0455877780914307, | |
| "eval_runtime": 48.528, | |
| "eval_samples_per_second": 16.094, | |
| "eval_steps_per_second": 8.057, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.024278392230914485, | |
| "grad_norm": 7.392975330352783, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 8.3295, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.026975991367682764, | |
| "grad_norm": 6.484737873077393, | |
| "learning_rate": 0.0, | |
| "loss": 7.8415, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.026975991367682764, | |
| "eval_loss": 2.045379638671875, | |
| "eval_runtime": 48.5278, | |
| "eval_samples_per_second": 16.094, | |
| "eval_steps_per_second": 8.057, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8850982419038208.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |